English
Related papers

Related papers: Stochastic Actor-Critic: Mitigating Overestimation…

200 papers

Continuous control of non-stationary environments is a major challenge for deep reinforcement learning algorithms. The time-dependency of the state transition dynamics aggravates the notorious stability problems of model-free deep…

Machine Learning · Computer Science 2025-11-05 Abdullah Akgül , Gulcin Baykal , Manuel Haußmann , Melih Kandemir

Scenario reduction algorithms can be an effective means to provide a tractable description of the uncertainty in optimal control problems. However, they might significantly compromise the performance of the controlled system. In this paper,…

Optimization and Control · Mathematics 2024-04-12 Francesco Cordiano , Bart De Schutter

Off-policy Actor-Critic algorithms have demonstrated phenomenal experimental performance but still require better explanations. To this end, we show its policy evaluation error on the distribution of transitions decomposes into: a Bellman…

Machine Learning · Computer Science 2021-10-07 Ting-Han Fan , Peter J. Ramadge

In the presence of multiscale dynamics in a reaction network, direct simulation methods become inefficient as they can only advance the system on the smallest scale. This work presents stochastic averaging techniques to accelerate…

Probability · Mathematics 2016-03-23 Araz Hashemi , Marcel Nunez , Petr Plechac , Dionisios G. Vlachos

Existing work on risk-sensitive reinforcement learning - both for symmetric and downside risk measures - has typically used direct Monte-Carlo estimation of policy gradients. While this approach yields unbiased gradient estimates, it also…

Machine Learning · Computer Science 2020-07-09 Thomas Spooner , Rahul Savani

In this paper, we investigate the issue of error accumulation in critic networks updated via pessimistic temporal difference objectives. We show that the critic approximation error can be approximated via a recursive fixed-point model…

Machine Learning · Computer Science 2024-03-05 Michal Nauman , Mateusz Ostaszewski , Marek Cygan

We identify a fundamental problem in policy gradient-based methods in continuous control. As policy gradient methods require the agent's underlying probability distribution, they limit policy representation to parametric distribution…

Machine Learning · Computer Science 2019-11-26 Chen Tessler , Guy Tennenholtz , Shie Mannor

In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the critic is exact, using the latter as a baseline is a variance-reduction method in a strong…

Machine Learning · Computer Science 2026-05-26 Safwan Labbi , Paul Mangold , Daniil Tiapkin , Eric Moulines

This paper explores the application of the Soft Actor-Critic (SAC) algorithm within a Distributional Reinforcement Learning setting and introduces an implementation of such algorithm named Cram\'er-based Distributional Soft Actor-Critic…

Machine Learning · Computer Science 2026-05-12 Vanya Aziz , Ivo Nowak , E. M. T Hendrix

Due to their complex nonlinear dynamics and batch-to-batch variability, batch processes pose a challenge for process control. Due to the absence of accurate models and resulting plant-model mismatch, these problems become harder to address…

Machine Learning · Computer Science 2022-05-03 Tanuja Joshi , Hariprasad Kodamana , Harikumar Kandath , Niket Kaisare

Actor-critic (AC) methods have exhibited great empirical success compared with other reinforcement learning algorithms, where the actor uses the policy gradient to improve the learning policy and the critic uses temporal difference learning…

Machine Learning · Computer Science 2022-10-11 Yue Wu , Weitong Zhang , Pan Xu , Quanquan Gu

Optimizing dynamic risk with stochastic policies is challenging in both policy updates and value learning. The former typically requires transition perturbation, while the latter may rely on model-based approaches. To address these…

Machine Learning · Computer Science 2026-05-11 Yudong Luo , Erick Delage

We present temporally abstract actor-critic (TAAC), a simple but effective off-policy RL algorithm that incorporates closed-loop temporal abstraction into the actor-critic framework. TAAC adds a second-stage binary policy to choose between…

Machine Learning · Computer Science 2021-10-13 Haonan Yu , Wei Xu , Haichao Zhang

As an important type of reinforcement learning algorithms, actor-critic (AC) and natural actor-critic (NAC) algorithms are often executed in two ways for finding optimal policies. In the first nested-loop design, actor's one update of…

Machine Learning · Computer Science 2020-05-11 Tengyu Xu , Zhe Wang , Yingbin Liang

Offline reinforcement learning (RL) is a promising approach for many control applications but faces challenges such as limited data coverage and value function overestimation. In this paper, we propose an implicit actor-critic (iAC)…

Machine Learning · Computer Science 2024-08-29 Vanshaj Khattar , Ming Jin

We address the problem of monitoring a set of binary stochastic processes and generating an alert when the number of anomalies among them exceeds a threshold. For this, the decision-maker selects and probes a subset of the processes to…

Machine Learning · Computer Science 2023-06-19 Geethu Joseph , M. Cenk Gursoy , Pramod K. Varshney

Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update weighted by the…

Machine Learning · Computer Science 2023-03-02 Samuel Neumann , Sungsu Lim , Ajin Joseph , Yangchen Pan , Adam White , Martha White

Actor-critic methods constitute a central paradigm in reinforcement learning (RL), coupling policy evaluation with policy improvement. While effective across many domains, these methods rely on separate actor and critic networks, which…

Machine Learning · Computer Science 2025-09-26 Donghyeon Ki , Hee-Jun Ahn , Kyungyoon Kim , Byung-Jun Lee

Actor-critic algorithms are widely used in reinforcement learning, but are challenging to mathematically analyse due to the online arrival of non-i.i.d. data samples. The distribution of the data samples dynamically changes as the model is…

Machine Learning · Computer Science 2023-09-20 Ziheng Wang , Justin Sirignano

The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this…

Machine Learning · Computer Science 2022-07-08 Samuele Tosatto , Andrew Patterson , Martha White , A. Rupam Mahmood